submission_id: chaiml-phase2-winner-13b2_v290
developer_uid: Danito42
alignment_samples: 0
best_of: 4
celo_rating: 841.66
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: 46803
num_wins: 5758
propriety_score: 0.6598214285714286
propriety_total_count: 2240.0
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: 2024-07-17T10:09:37+00:00
us_pacific_date: 2024-07-17
win_ratio: 0.12302630173279491
Resubmit model
Running pipeline stage MKMLizer
Starting job with name chaiml-phase2-winner-13b2-v290-mkmlizer
Waiting for job on chaiml-phase2-winner-13b2-v290-mkmlizer to finish
Stopping job with name chaiml-phase2-winner-13b2-v290-mkmlizer
%s, retrying in %s seconds...
Starting job with name chaiml-phase2-winner-13b2-v290-mkmlizer
Waiting for job on chaiml-phase2-winner-13b2-v290-mkmlizer to finish
chaiml-phase2-winner-13b2-v290-mkmlizer: ╔═════════════════════════════════════════════════════════════════════╗
chaiml-phase2-winner-13b2-v290-mkmlizer: ║ _____ __ __ ║
chaiml-phase2-winner-13b2-v290-mkmlizer: ║ / _/ /_ ___ __/ / ___ ___ / / ║
chaiml-phase2-winner-13b2-v290-mkmlizer: ║ / _/ / // / |/|/ / _ \/ -_) -_) / ║
chaiml-phase2-winner-13b2-v290-mkmlizer: ║ /_//_/\_, /|__,__/_//_/\__/\__/_/ ║
chaiml-phase2-winner-13b2-v290-mkmlizer: ║ /___/ ║
chaiml-phase2-winner-13b2-v290-mkmlizer: ║ ║
chaiml-phase2-winner-13b2-v290-mkmlizer: ║ Version: 0.9.5.post2 ║
chaiml-phase2-winner-13b2-v290-mkmlizer: ║ Copyright 2023 MK ONE TECHNOLOGIES Inc. ║
chaiml-phase2-winner-13b2-v290-mkmlizer: ║ https://mk1.ai ║
chaiml-phase2-winner-13b2-v290-mkmlizer: ║ ║
chaiml-phase2-winner-13b2-v290-mkmlizer: ║ The license key for the current software has been verified as ║
chaiml-phase2-winner-13b2-v290-mkmlizer: ║ belonging to: ║
chaiml-phase2-winner-13b2-v290-mkmlizer: ║ ║
chaiml-phase2-winner-13b2-v290-mkmlizer: ║ Chai Research Corp. ║
chaiml-phase2-winner-13b2-v290-mkmlizer: ║ Account ID: 7997a29f-0ceb-4cc7-9adf-840c57b4ae6f ║
chaiml-phase2-winner-13b2-v290-mkmlizer: ║ Expiration: 2024-10-15 23:59:59 ║
chaiml-phase2-winner-13b2-v290-mkmlizer: ║ ║
chaiml-phase2-winner-13b2-v290-mkmlizer: ╚═════════════════════════════════════════════════════════════════════╝
Connection pool is full, discarding connection: %s. Connection pool size: %s
chaiml-phase2-winner-13b2-v290-mkmlizer: Downloaded to shared memory in 37.067s
chaiml-phase2-winner-13b2-v290-mkmlizer: quantizing model to /dev/shm/model_cache
chaiml-phase2-winner-13b2-v290-mkmlizer: Saving flywheel model at /dev/shm/model_cache
chaiml-phase2-winner-13b2-v290-mkmlizer: model.embed_tokens.weight torch.Size([43520000])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.0.self_attn.qkv_proj.weight torch.Size([15974400])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.0.self_attn.o_proj.weight torch.Size([5324800])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.0.mlp.down_proj.weight torch.Size([14376960])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.0.mlp.up_gate_proj.weight torch.Size([28753920])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.0.input_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.0.post_attention_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.1.self_attn.qkv_proj.weight torch.Size([15974400])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.1.self_attn.o_proj.weight torch.Size([5324800])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.1.mlp.down_proj.weight torch.Size([14376960])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.1.mlp.up_gate_proj.weight torch.Size([28753920])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.1.input_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.1.post_attention_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.2.self_attn.qkv_proj.weight torch.Size([15974400])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.2.self_attn.o_proj.weight torch.Size([5324800])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.2.mlp.down_proj.weight torch.Size([14376960])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.2.mlp.up_gate_proj.weight torch.Size([28753920])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.2.input_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.2.post_attention_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.3.self_attn.qkv_proj.weight torch.Size([15974400])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.3.self_attn.o_proj.weight torch.Size([5324800])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.3.mlp.down_proj.weight torch.Size([14376960])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.3.mlp.up_gate_proj.weight torch.Size([28753920])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.3.input_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.3.post_attention_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.4.self_attn.qkv_proj.weight torch.Size([15974400])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.4.self_attn.o_proj.weight torch.Size([5324800])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.4.mlp.down_proj.weight torch.Size([14376960])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.4.mlp.up_gate_proj.weight torch.Size([28753920])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.4.input_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.4.post_attention_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.5.self_attn.qkv_proj.weight torch.Size([15974400])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.5.self_attn.o_proj.weight torch.Size([5324800])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.5.mlp.down_proj.weight torch.Size([14376960])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.5.mlp.up_gate_proj.weight torch.Size([28753920])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.5.input_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.5.post_attention_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.6.self_attn.qkv_proj.weight torch.Size([15974400])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.6.self_attn.o_proj.weight torch.Size([5324800])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.6.mlp.down_proj.weight torch.Size([14376960])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.6.mlp.up_gate_proj.weight torch.Size([28753920])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.6.input_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.6.post_attention_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.7.self_attn.qkv_proj.weight torch.Size([15974400])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.7.self_attn.o_proj.weight torch.Size([5324800])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.7.mlp.down_proj.weight torch.Size([14376960])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.7.mlp.up_gate_proj.weight torch.Size([28753920])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.7.input_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.7.post_attention_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.8.self_attn.qkv_proj.weight torch.Size([15974400])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.8.self_attn.o_proj.weight torch.Size([5324800])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.8.mlp.down_proj.weight torch.Size([14376960])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.8.mlp.up_gate_proj.weight torch.Size([28753920])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.8.input_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.8.post_attention_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.9.self_attn.qkv_proj.weight torch.Size([15974400])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.9.self_attn.o_proj.weight torch.Size([5324800])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.9.mlp.down_proj.weight torch.Size([14376960])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.9.mlp.up_gate_proj.weight torch.Size([28753920])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.9.input_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.9.post_attention_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.10.self_attn.qkv_proj.weight torch.Size([15974400])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.10.self_attn.o_proj.weight torch.Size([5324800])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.10.mlp.down_proj.weight torch.Size([14376960])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.10.mlp.up_gate_proj.weight torch.Size([28753920])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.10.input_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.10.post_attention_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.11.self_attn.qkv_proj.weight torch.Size([15974400])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.11.self_attn.o_proj.weight torch.Size([5324800])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.11.mlp.down_proj.weight torch.Size([14376960])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.11.mlp.up_gate_proj.weight torch.Size([28753920])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.11.input_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.11.post_attention_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.12.self_attn.qkv_proj.weight torch.Size([15974400])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.12.self_attn.o_proj.weight torch.Size([5324800])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.12.mlp.down_proj.weight torch.Size([14376960])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.12.mlp.up_gate_proj.weight torch.Size([28753920])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.12.input_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.12.post_attention_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.13.self_attn.qkv_proj.weight torch.Size([15974400])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.13.self_attn.o_proj.weight torch.Size([5324800])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.13.mlp.down_proj.weight torch.Size([14376960])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.13.mlp.up_gate_proj.weight torch.Size([28753920])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.13.input_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.13.post_attention_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.14.self_attn.qkv_proj.weight torch.Size([15974400])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.14.self_attn.o_proj.weight torch.Size([5324800])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.14.mlp.down_proj.weight torch.Size([14376960])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.14.mlp.up_gate_proj.weight torch.Size([28753920])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.14.input_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.14.post_attention_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.15.self_attn.qkv_proj.weight torch.Size([15974400])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.15.self_attn.o_proj.weight torch.Size([5324800])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.15.mlp.down_proj.weight torch.Size([14376960])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.15.mlp.up_gate_proj.weight torch.Size([28753920])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.15.input_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.15.post_attention_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.16.self_attn.qkv_proj.weight torch.Size([15974400])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.16.self_attn.o_proj.weight torch.Size([5324800])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.16.mlp.down_proj.weight torch.Size([14376960])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.16.mlp.up_gate_proj.weight torch.Size([28753920])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.16.input_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.16.post_attention_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.17.self_attn.qkv_proj.weight torch.Size([15974400])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.17.self_attn.o_proj.weight torch.Size([5324800])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.17.mlp.down_proj.weight torch.Size([14376960])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.17.mlp.up_gate_proj.weight torch.Size([28753920])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.17.input_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.17.post_attention_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.18.self_attn.qkv_proj.weight torch.Size([15974400])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.18.self_attn.o_proj.weight torch.Size([5324800])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.18.mlp.down_proj.weight torch.Size([14376960])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.18.mlp.up_gate_proj.weight torch.Size([28753920])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.18.input_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.18.post_attention_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.19.self_attn.qkv_proj.weight torch.Size([15974400])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.19.self_attn.o_proj.weight torch.Size([5324800])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.19.mlp.down_proj.weight torch.Size([14376960])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.19.mlp.up_gate_proj.weight torch.Size([28753920])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.19.input_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.19.post_attention_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.20.self_attn.qkv_proj.weight torch.Size([15974400])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.20.self_attn.o_proj.weight torch.Size([5324800])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.20.mlp.down_proj.weight torch.Size([14376960])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.20.mlp.up_gate_proj.weight torch.Size([28753920])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.20.input_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.20.post_attention_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.21.self_attn.qkv_proj.weight torch.Size([15974400])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.21.self_attn.o_proj.weight torch.Size([5324800])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.21.mlp.down_proj.weight torch.Size([14376960])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.21.mlp.up_gate_proj.weight torch.Size([28753920])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.21.input_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.21.post_attention_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.22.self_attn.qkv_proj.weight torch.Size([15974400])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.22.self_attn.o_proj.weight torch.Size([5324800])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.22.mlp.down_proj.weight torch.Size([14376960])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.22.mlp.up_gate_proj.weight torch.Size([28753920])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.22.input_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.22.post_attention_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.23.self_attn.qkv_proj.weight torch.Size([15974400])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.23.self_attn.o_proj.weight torch.Size([5324800])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.23.mlp.down_proj.weight torch.Size([14376960])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.23.mlp.up_gate_proj.weight torch.Size([28753920])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.23.input_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.23.post_attention_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.24.self_attn.qkv_proj.weight torch.Size([15974400])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.24.self_attn.o_proj.weight torch.Size([5324800])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.24.mlp.down_proj.weight torch.Size([14376960])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.24.mlp.up_gate_proj.weight torch.Size([28753920])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.24.input_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.24.post_attention_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.25.self_attn.qkv_proj.weight torch.Size([15974400])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.25.self_attn.o_proj.weight torch.Size([5324800])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.25.mlp.down_proj.weight torch.Size([14376960])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.25.mlp.up_gate_proj.weight torch.Size([28753920])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.25.input_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.25.post_attention_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: Loading 0: 0%| | 0/403 [00:00<?, ?it/s] Loading 0: 1%| | 3/403 [00:00<00:03, 118.84it/s] Loading 0: 1%| | 4/403 [00:00<00:02, 155.52it/s] Loading 0: 2%|▏ | 7/403 [00:00<00:01, 264.25it/s] Loading 0: 2%|▏ | 8/403 [00:00<00:01, 296.94it/s] Loading 0: 2%|▏ | 9/403 [00:00<00:01, 332.28it/s] Loading 0: 2%|▏ | 10/403 [00:00<00:01, 367.60it/s] Loading 0: 3%|▎ | 13/403 [00:00<00:00, 472.29it/s] Loading 0: 3%|▎ | 14/403 [00:00<00:00, 500.54it/s] Loading 0: 4%|▍ | 17/403 [00:00<00:00, 591.52it/s] Loading 0: 4%|▍ | 18/403 [00:00<00:00, 616.82it/s] Loading 0: 5%|▍ | 19/403 [00:00<00:00, 648.09it/s] Loading 0: 5%|▍ | 20/403 [00:00<00:00, 679.58it/s] Loading 0: 6%|▌ | 23/403 [00:00<00:00, 773.04it/s] Loading 0: 6%|▌ | 24/403 [00:00<00:00, 794.87it/s] Loading 0: 7%|▋ | 27/403 [00:00<00:00, 879.00it/s] Loading 0: 7%|▋ | 28/403 [00:00<00:00, 898.91it/s] Loading 0: 7%|▋ | 29/403 [00:00<00:00, 927.19it/s] Loading 0: 7%|▋ | 30/403 [00:00<00:00, 955.73it/s] Loading 0: 8%|▊ | 33/403 [00:00<00:00, 1040.77it/s] Loading 0: 8%|▊ | 34/403 [00:00<00:00, 1057.93it/s] Loading 0: 9%|▉ | 37/403 [00:00<00:00, 1132.47it/s] Loading 0: 9%|▉ | 38/403 [00:00<00:00, 1147.99it/s] Loading 0: 10%|▉ | 39/403 [00:00<00:00, 1173.50it/s] Loading 0: 10%|▉ | 40/403 [00:00<00:00, 1199.55it/s] Loading 0: 11%|█ | 43/403 [00:00<00:00, 1277.70it/s] Loading 0: 11%|█ | 44/403 [00:00<00:00, 1291.02it/s] Loading 0: 12%|█▏ | 47/403 [00:00<00:00, 1358.61it/s] Loading 0: 12%|█▏ | 48/403 [00:00<00:00, 1370.74it/s] Loading 0: 12%|█▏ | 49/403 [00:00<00:00, 1393.92it/s] Loading 0: 12%|█▏ | 50/403 [00:00<00:00, 1417.93it/s] Loading 0: 13%|█▎ | 53/403 [00:00<00:00, 1489.66it/s] Loading 0: 13%|█▎ | 54/403 [00:00<00:00, 1500.48it/s] Loading 0: 14%|█▍ | 57/403 [00:00<00:00, 1557.45it/s] Loading 0: 14%|█▍ | 58/403 [00:00<00:00, 1566.39it/s] Loading 0: 15%|█▍ | 59/403 [00:00<00:00, 1587.73it/s] Loading 0: 15%|█▍ | 60/403 [00:00<00:00, 1609.73it/s] Loading 0: 16%|█▌ | 63/403 [00:00<00:00, 1676.24it/s] Loading 0: 16%|█▌ | 64/403 [00:00<00:00, 1684.51it/s] Loading 0: 17%|█▋ | 67/403 [00:00<00:00, 1738.52it/s] Loading 0: 17%|█▋ | 68/403 [00:00<00:00, 1744.76it/s] Loading 0: 17%|█▋ | 69/403 [00:00<00:00, 1764.76it/s] Loading 0: 17%|█▋ | 70/403 [00:00<00:00, 1785.34it/s] Loading 0: 18%|█▊ | 73/403 [00:00<00:00, 1847.12it/s] Loading 0: 18%|█▊ | 74/403 [00:00<00:00, 1852.94it/s] Loading 0: 19%|█▉ | 77/403 [00:00<00:00, 1901.74it/s] Loading 0: 19%|█▉ | 78/403 [00:00<00:00, 1906.12it/s] Loading 0: 20%|█▉ | 79/403 [00:00<00:00, 1924.57it/s] Loading 0: 20%|█▉ | 80/403 [00:00<00:00, 1943.69it/s] Loading 0: 21%|██ | 83/403 [00:00<00:00, 2001.23it/s] Loading 0: 21%|██ | 84/403 [00:00<00:00, 2005.71it/s] Loading 0: 22%|██▏ | 87/403 [00:00<00:00, 2050.29it/s] Loading 0: 22%|██▏ | 88/403 [00:00<00:00, 2053.35it/s] Loading 0: 22%|██▏ | 89/403 [00:00<00:00, 2070.27it/s] Loading 0: 22%|██▏ | 90/403 [00:00<00:00, 2088.18it/s] Loading 0: 23%|██▎ | 93/403 [00:00<00:00, 2141.89it/s] Loading 0: 23%|██▎ | 94/403 [00:00<00:00, 2145.18it/s] Loading 0: 24%|██▍ | 97/403 [00:00<00:00, 2186.18it/s] Loading 0: 24%|██▍ | 98/403 [00:00<00:00, 2187.64it/s] Loading 0: 25%|██▍ | 99/403 [00:00<00:00, 2203.51it/s] Loading 0: 25%|██▍ | 100/403 [00:00<00:00, 2220.31it/s] Loading 0: 26%|██▌ | 103/403 [00:00<00:00, 2271.34it/s] Loading 0: 26%|██▌ | 104/403 [00:00<00:00, 2273.06it/s] Loading 0: 27%|██▋ | 107/403 [00:00<00:00, 2311.43it/s] Loading 0: 27%|██▋ | 108/403 [00:00<00:00, 2311.43it/s] Loading 0: 27%|██▋ | 109/403 [00:00<00:00, 2326.62it/s] Loading 0: 27%|██▋ | 110/403 [00:00<00:00, 2342.53it/s] Loading 0: 28%|██▊ | 113/403 [00:00<00:00, 2389.54it/s] Loading 0: 28%|██▊ | 114/403 [00:00<00:00, 2390.43it/s] Loading 0: 29%|██▉ | 117/403 [00:00<00:00, 2425.54it/s] Loading 0: 29%|██▉ | 118/403 [00:00<00:00, 2424.77it/s] Loading 0: 30%|██▉ | 119/403 [00:00<00:00, 2438.78it/s] Loading 0: 30%|██▉ | 120/403 [00:00<00:00, 2453.69it/s] Loading 0: 31%|███ | 123/403 [00:00<00:00, 2498.99it/s] Loading 0: 31%|███ | 124/403 [00:00<00:00, 2498.20it/s] Loading 0: 32%|███▏ | 127/403 [00:00<00:00, 2530.47it/s] Loading 0: 32%|███▏ | 128/403 [00:00<00:00, 2528.78it/s] Loading 0: 32%|███▏ | 129/403 [00:00<00:00, 2541.93it/s] Loading 0: 32%|███▏ | 130/403 [00:00<00:00, 2556.04it/s] Loading 0: 33%|███▎ | 133/403 [00:00<00:00, 2599.49it/s] Loading 0: 33%|███▎ | 134/403 [00:00<00:00, 2598.34it/s] Loading 0: 34%|███▍ | 137/403 [00:00<00:00, 2629.13it/s] Loading 0: 34%|███▍ | 138/403 [00:00<00:00, 2624.84it/s] Loading 0: 34%|███▍ | 139/403 [00:00<00:00, 2637.41it/s] Loading 0: 35%|███▍ | 140/403 [00:00<00:00, 2650.36it/s] Loading 0: 35%|███▌ | 143/403 [00:00<00:00, 2690.73it/s] Loading 0: 36%|███▌ | 144/403 [00:00<00:00, 2688.27it/s] Loading 0: 36%|███▋ | 147/403 [00:00<00:00, 2718.07it/s] Loading 0: 37%|███▋ | 148/403 [00:00<00:00, 2705.12it/s] Loading 0: 37%|███▋ | 149/403 [00:00<00:00, 2717.38it/s] Loading 0: 37%|███▋ | 150/403 [00:00<00:00, 2730.37it/s] Loading 0: 38%|███▊ | 153/403 [00:02<00:03, 66.61it/s] Loading 0: 38%|███▊ | 154/403 [00:02<00:03, 67.04it/s] Loading 0: 38%|███▊ | 154/403 [00:02<00:03, 67.04it/s] Loading 0: 39%|███▉ | 157/403 [00:02<00:03, 67.04it/s] Loading 0: 39%|███▉ | 158/403 [00:02<00:03, 67.04it/s] Loading 0: 39%|███▉ | 159/403 [00:02<00:03, 67.04it/s] Loading 0: 40%|███▉ | 160/403 [00:02<00:03, 67.04it/s] Loading 0: 40%|████ | 163/403 [00:02<00:03, 67.04it/s] Loading 0: 41%|████ | 164/403 [00:02<00:03, 67.04it/s] Loading 0: 41%|████▏ | 167/403 [00:02<00:03, 67.04it/s] Loading 0: 42%|████▏ | 168/403 [00:02<00:03, 67.04it/s] Loading 0: 42%|████▏ | 169/403 [00:02<00:03, 67.04it/s] Loading 0: 42%|████▏ | 170/403 [00:02<00:03, 67.04it/s] Loading 0: 43%|████▎ | 173/403 [00:02<00:03, 67.04it/s] Loading 0: 43%|████▎ | 174/403 [00:02<00:03, 67.04it/s] Loading 0: 44%|████▍ | 177/403 [00:02<00:03, 67.04it/s] Loading 0: 44%|████▍ | 178/403 [00:02<00:03, 67.04it/s] Loading 0: 44%|████▍ | 179/403 [00:02<00:03, 67.04it/s] Loading 0: 45%|████▍ | 180/403 [00:02<00:03, 67.04it/s] Loading 0: 45%|████▌ | 183/403 [00:02<00:03, 67.04it/s] Loading 0: 46%|████▌ | 184/403 [00:02<00:03, 67.04it/s] Loading 0: 46%|████▋ | 187/403 [00:02<00:03, 67.04it/s] Loading 0: 47%|████▋ | 188/403 [00:02<00:03, 67.04it/s] Loading 0: 47%|████▋ | 189/403 [00:02<00:03, 67.04it/s] Loading 0: 47%|████▋ | 190/403 [00:02<00:03, 67.04it/s] Loading 0: 48%|████▊ | 193/403 [00:02<00:03, 67.04it/s] Loading 0: 48%|████▊ | 194/403 [00:02<00:03, 67.04it/s] Loading 0: 49%|████▉ | 197/403 [00:02<00:03, 67.04it/s] Loading 0: 49%|████▉ | 198/403 [00:02<00:03, 67.04it/s] Loading 0: 49%|████▉ | 199/403 [00:02<00:03, 67.04it/s] Loading 0: 50%|████▉ | 200/403 [00:02<00:03, 67.04it/s] Loading 0: 50%|█████ | 203/403 [00:02<00:02, 67.04it/s] Loading 0: 51%|█████ | 204/403 [00:02<00:02, 67.04it/s] Loading 0: 51%|█████▏ | 207/403 [00:02<00:02, 67.04it/s] Loading 0: 52%|█████▏ | 208/403 [00:02<00:02, 67.04it/s] Loading 0: 52%|█model.layers.26.self_attn.qkv_proj.weight torch.Size([15974400])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.26.self_attn.o_proj.weight torch.Size([5324800])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.26.mlp.down_proj.weight torch.Size([14376960])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.26.mlp.up_gate_proj.weight torch.Size([28753920])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.26.input_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.26.post_attention_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.27.self_attn.qkv_proj.weight torch.Size([15974400])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.27.self_attn.o_proj.weight torch.Size([5324800])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.27.mlp.down_proj.weight torch.Size([14376960])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.27.mlp.up_gate_proj.weight torch.Size([28753920])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.27.input_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.27.post_attention_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.28.self_attn.qkv_proj.weight torch.Size([15974400])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.28.self_attn.o_proj.weight torch.Size([5324800])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.28.mlp.down_proj.weight torch.Size([14376960])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.28.mlp.up_gate_proj.weight torch.Size([28753920])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.28.input_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.28.post_attention_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.29.self_attn.qkv_proj.weight torch.Size([15974400])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.29.self_attn.o_proj.weight torch.Size([5324800])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.29.mlp.down_proj.weight torch.Size([14376960])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.29.mlp.up_gate_proj.weight torch.Size([28753920])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.29.input_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.29.post_attention_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.30.self_attn.qkv_proj.weight torch.Size([15974400])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.30.self_attn.o_proj.weight torch.Size([5324800])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.30.mlp.down_proj.weight torch.Size([14376960])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.30.mlp.up_gate_proj.weight torch.Size([28753920])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.30.input_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.30.post_attention_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.31.self_attn.qkv_proj.weight torch.Size([15974400])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.31.self_attn.o_proj.weight torch.Size([5324800])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.31.mlp.down_proj.weight torch.Size([14376960])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.31.mlp.up_gate_proj.weight torch.Size([28753920])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.31.input_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.31.post_attention_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.32.self_attn.qkv_proj.weight torch.Size([15974400])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.32.self_attn.o_proj.weight torch.Size([5324800])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.32.mlp.down_proj.weight torch.Size([14376960])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.32.mlp.up_gate_proj.weight torch.Size([28753920])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.32.input_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.32.post_attention_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.33.self_attn.qkv_proj.weight torch.Size([15974400])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.33.self_attn.o_proj.weight torch.Size([5324800])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.33.mlp.down_proj.weight torch.Size([14376960])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.33.mlp.up_gate_proj.weight torch.Size([28753920])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.33.input_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.33.post_attention_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.34.self_attn.qkv_proj.weight torch.Size([15974400])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.34.self_attn.o_proj.weight torch.Size([5324800])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.34.mlp.down_proj.weight torch.Size([14376960])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.34.mlp.up_gate_proj.weight torch.Size([28753920])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.34.input_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.34.post_attention_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.35.self_attn.qkv_proj.weight torch.Size([15974400])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.35.self_attn.o_proj.weight torch.Size([5324800])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.35.mlp.down_proj.weight torch.Size([14376960])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.35.mlp.up_gate_proj.weight torch.Size([28753920])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.35.input_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.35.post_attention_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.36.self_attn.qkv_proj.weight torch.Size([15974400])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.36.self_attn.o_proj.weight torch.Size([5324800])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.36.mlp.down_proj.weight torch.Size([14376960])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.36.mlp.up_gate_proj.weight torch.Size([28753920])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.36.input_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.36.post_attention_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.37.self_attn.qkv_proj.weight torch.Size([15974400])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.37.self_attn.o_proj.weight torch.Size([5324800])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.37.mlp.down_proj.weight torch.Size([14376960])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.37.mlp.up_gate_proj.weight torch.Size([28753920])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.37.input_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.37.post_attention_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.38.self_attn.qkv_proj.weight torch.Size([15974400])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.38.self_attn.o_proj.weight torch.Size([5324800])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.38.mlp.down_proj.weight torch.Size([14376960])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.38.mlp.up_gate_proj.weight torch.Size([28753920])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.38.input_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.38.post_attention_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.39.self_attn.qkv_proj.weight torch.Size([15974400])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.39.self_attn.o_proj.weight torch.Size([5324800])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.39.mlp.down_proj.weight torch.Size([14376960])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.39.mlp.up_gate_proj.weight torch.Size([28753920])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.39.input_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.layers.39.post_attention_layernorm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: model.norm.weight torch.Size([5120])
chaiml-phase2-winner-13b2-v290-mkmlizer: lm_head.weight torch.Size([43520000])
chaiml-phase2-winner-13b2-v290-mkmlizer: quantized model in 26.721s
chaiml-phase2-winner-13b2-v290-mkmlizer: Processed model ChaiML/phase2_winner_13b2 in 63.788s
chaiml-phase2-winner-13b2-v290-mkmlizer: creating bucket guanaco-mkml-models
chaiml-phase2-winner-13b2-v290-mkmlizer: Bucket 's3://guanaco-mkml-models/' created
chaiml-phase2-winner-13b2-v290-mkmlizer: uploading /dev/shm/model_cache to s3://guanaco-mkml-models/chaiml-phase2-winner-13b2-v290
chaiml-phase2-winner-13b2-v290-mkmlizer: cp /dev/shm/model_cache/special_tokens_map.json s3://guanaco-mkml-models/chaiml-phase2-winner-13b2-v290/special_tokens_map.json
chaiml-phase2-winner-13b2-v290-mkmlizer: cp /dev/shm/model_cache/config.json s3://guanaco-mkml-models/chaiml-phase2-winner-13b2-v290/config.json
chaiml-phase2-winner-13b2-v290-mkmlizer: cp /dev/shm/model_cache/tokenizer.model s3://guanaco-mkml-models/chaiml-phase2-winner-13b2-v290/tokenizer.model
chaiml-phase2-winner-13b2-v290-mkmlizer: cp /dev/shm/model_cache/tokenizer.json s3://guanaco-mkml-models/chaiml-phase2-winner-13b2-v290/tokenizer.json
chaiml-phase2-winner-13b2-v290-mkmlizer: cp /dev/shm/model_cache/tokenizer_config.json s3://guanaco-mkml-models/chaiml-phase2-winner-13b2-v290/tokenizer_config.json
chaiml-phase2-winner-13b2-v290-mkmlizer: cp /dev/shm/model_cache/flywheel_model.0.safetensors s3://guanaco-mkml-models/chaiml-phase2-winner-13b2-v290/flywheel_model.0.safetensors
chaiml-phase2-winner-13b2-v290-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-v290-mkmlizer: warnings.warn(
chaiml-phase2-winner-13b2-v290-mkmlizer: Saving model to /tmp/reward_cache/reward.tensors
chaiml-phase2-winner-13b2-v290-mkmlizer: Saving duration: 0.394s
chaiml-phase2-winner-13b2-v290-mkmlizer: Processed model ChaiML/reward_gpt2_medium_preference_24m_e2 in 5.481s
chaiml-phase2-winner-13b2-v290-mkmlizer: creating bucket guanaco-reward-models
chaiml-phase2-winner-13b2-v290-mkmlizer: Bucket 's3://guanaco-reward-models/' created
chaiml-phase2-winner-13b2-v290-mkmlizer: uploading /tmp/reward_cache to s3://guanaco-reward-models/chaiml-phase2-winner-13b2-v290_reward
chaiml-phase2-winner-13b2-v290-mkmlizer: cp /tmp/reward_cache/config.json s3://guanaco-reward-models/chaiml-phase2-winner-13b2-v290_reward/config.json
chaiml-phase2-winner-13b2-v290-mkmlizer: cp /tmp/reward_cache/special_tokens_map.json s3://guanaco-reward-models/chaiml-phase2-winner-13b2-v290_reward/special_tokens_map.json
chaiml-phase2-winner-13b2-v290-mkmlizer: cp /tmp/reward_cache/tokenizer_config.json s3://guanaco-reward-models/chaiml-phase2-winner-13b2-v290_reward/tokenizer_config.json
chaiml-phase2-winner-13b2-v290-mkmlizer: cp /tmp/reward_cache/vocab.json s3://guanaco-reward-models/chaiml-phase2-winner-13b2-v290_reward/vocab.json
chaiml-phase2-winner-13b2-v290-mkmlizer: cp /tmp/reward_cache/tokenizer.json s3://guanaco-reward-models/chaiml-phase2-winner-13b2-v290_reward/tokenizer.json
chaiml-phase2-winner-13b2-v290-mkmlizer: cp /tmp/reward_cache/merges.txt s3://guanaco-reward-models/chaiml-phase2-winner-13b2-v290_reward/merges.txt
chaiml-phase2-winner-13b2-v290-mkmlizer: cp /tmp/reward_cache/reward.tensors s3://guanaco-reward-models/chaiml-phase2-winner-13b2-v290_reward/reward.tensors
Job chaiml-phase2-winner-13b2-v290-mkmlizer completed after 106.83s with status: succeeded
Stopping job with name chaiml-phase2-winner-13b2-v290-mkmlizer
Pipeline stage MKMLizer completed in 108.16s
Running pipeline stage MKMLKubeTemplater
Pipeline stage MKMLKubeTemplater completed in 0.15s
Running pipeline stage ISVCDeployer
Creating inference service chaiml-phase2-winner-13b2-v290
Waiting for inference service chaiml-phase2-winner-13b2-v290 to be ready
Inference service chaiml-phase2-winner-13b2-v290 ready after 40.18862986564636s
Pipeline stage ISVCDeployer completed in 47.29s
Running pipeline stage StressChecker
Received healthy response to inference request in 2.420884847640991s
Received healthy response to inference request in 1.5709099769592285s
Received healthy response to inference request in 1.6538777351379395s
Received healthy response to inference request in 1.6271393299102783s
Received healthy response to inference request in 1.6568832397460938s
5 requests
0 failed requests
5th percentile: 1.5821558475494384
10th percentile: 1.5934017181396485
20th percentile: 1.6158934593200684
30th percentile: 1.6324870109558105
40th percentile: 1.643182373046875
50th percentile: 1.6538777351379395
60th percentile: 1.6550799369812013
70th percentile: 1.6562821388244628
80th percentile: 1.8096835613250735
90th percentile: 2.1152842044830322
95th percentile: 2.2680845260620117
99th percentile: 2.3903247833251955
mean time: 1.7859390258789063
Pipeline stage StressChecker completed in 10.46s
chaiml-phase2-winner-13b2_v290 status is now deployed due to DeploymentManager action
chaiml-phase2-winner-13b2_v290 status is now inactive due to auto deactivation removed underperforming models
admin requested tearing down of chaiml-phase2-winner-13b2_v290
Running pipeline stage ISVCDeleter
Checking if service chaiml-phase2-winner-13b2-v290 is running
Skipping teardown as no inference service was found
Pipeline stage ISVCDeleter completed in 4.84s
Running pipeline stage MKMLModelDeleter
Cleaning model data from S3
Cleaning model data from model cache
Deleting key chaiml-phase2-winner-13b2-v290/config.json from bucket guanaco-mkml-models
Deleting key chaiml-phase2-winner-13b2-v290/flywheel_model.0.safetensors from bucket guanaco-mkml-models
Deleting key chaiml-phase2-winner-13b2-v290/special_tokens_map.json from bucket guanaco-mkml-models
Deleting key chaiml-phase2-winner-13b2-v290/tokenizer.json from bucket guanaco-mkml-models
Deleting key chaiml-phase2-winner-13b2-v290/tokenizer.model from bucket guanaco-mkml-models
Deleting key chaiml-phase2-winner-13b2-v290/tokenizer_config.json from bucket guanaco-mkml-models
Cleaning model data from model cache
Deleting key chaiml-phase2-winner-13b2-v290_reward/config.json from bucket guanaco-reward-models
Deleting key chaiml-phase2-winner-13b2-v290_reward/merges.txt from bucket guanaco-reward-models
Deleting key chaiml-phase2-winner-13b2-v290_reward/reward.tensors from bucket guanaco-reward-models
Deleting key chaiml-phase2-winner-13b2-v290_reward/special_tokens_map.json from bucket guanaco-reward-models
Deleting key chaiml-phase2-winner-13b2-v290_reward/tokenizer.json from bucket guanaco-reward-models
Deleting key chaiml-phase2-winner-13b2-v290_reward/tokenizer_config.json from bucket guanaco-reward-models
Deleting key chaiml-phase2-winner-13b2-v290_reward/vocab.json from bucket guanaco-reward-models
Pipeline stage MKMLModelDeleter completed in 8.67s
chaiml-phase2-winner-13b2_v290 status is now torndown due to DeploymentManager action

Usage Metrics

Latency Metrics