eval results

out/pretrain/final/evaluate/config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d68796194460465eef693c3a2a4dfc2df61655c8a7e8c9119ac22c07bd9e7f27
+size 547

out/pretrain/final/evaluate/model_config.yaml

@@ -0,0 +1,33 @@
+attention_logit_softcapping: null
+attention_scores_scalar: null
+bias: false
+block_size: 32768
+final_logit_softcapping: null
+gelu_approximate: none
+head_size: 16
+hf_config: {}
+intermediate_size: 2048
+lm_head_bias: false
+mlp_class_name: LLaMAMLP
+n_embd: 512
+n_expert: 0
+n_expert_per_token: 0
+n_head: 32
+n_layer: 20
+n_query_groups: 4
+name: ''
+norm_class_name: RMSNorm
+norm_eps: 1.0e-05
+padded_vocab_size: 32768
+padding_multiple: 512
+parallel_residual: false
+post_attention_norm: false
+post_mlp_norm: false
+rope_base: 500000
+rope_condense_ratio: 1
+rotary_percentage: 1.0
+scale_embeddings: false
+shared_attention_norm: false
+sliding_window_layer_placing: null
+sliding_window_size: null
+vocab_size: 32768

out/pretrain/final/evaluate/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab60761622286ea11d7ce9f33d6865aa01e9300c9cd59ebf201b20db15aee8ac
+size 216632102

out/pretrain/final/evaluate/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b496a30dc268bcb8adfd551f693e68e9eadd06b81cab385c088a61e7663649c
+size 1368561

out/pretrain/final/evaluate/tokenizer_config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6333d68c3280be6081b795cc160fd5872707562021f9889b2e2bd3ae508fa62
+size 23043