Training in progress, step 500

config.json

@@ -1 +1 @@
-{"d_model": 1024, "in_feas": 116, "n_layer": 4, "vocab_size": 140, "ssm_cfg": {}, "rms_norm": true, "residual_in_fp32": true, "fused_add_norm": true}
+{"d_model": 1024, "in_feas": 360, "n_layer": 4, "vocab_size": 176, "ssm_cfg": {}, "rms_norm": true, "residual_in_fp32": true, "fused_add_norm": true}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c1636bf6559b304fbc8e9754e60a22d56a79b5caa6326a0de7cbb9cc20ff7c3
-size 107193141
+oid sha256:85d570c4f5dfcf32c6ef3ea3fda691e2a0a86da9fd0a4befb002e1bb1974b7d9
+size 108204853

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e61c5120e5c4ed9deba4d418396ec1531c5a5bfe40df32d562fd5463735e8c3
+oid sha256:1b7d3cccda951a13ac2819b047a46a705aae529de441d499637362d6016380ef
 size 4920