Training in progress, step 52

config.json

@@ -1 +1 @@
-{"d_model": 768, "n_layer": 24, "vocab_size": 50277, "ssm_cfg": {}, "rms_norm": true, "residual_in_fp32": true, "fused_add_norm": true, "pad_vocab_size_multiple": 8, "tie_embeddings": false}
+{"d_model": 1024, "n_layer": 48, "vocab_size": 50277, "ssm_cfg": {}, "rms_norm": true, "residual_in_fp32": true, "fused_add_norm": true, "pad_vocab_size_multiple": 8, "tie_embeddings": false}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a47e1392bdd48fc4b617be0c9f91ced1278d89ce34f64a6bb444ab58c6b87a7
-size 516640282
+oid sha256:710378077ca6fe9314cddf6377b4fa5fc2c226bd88bde21829f91deeaa2d4487
+size 1486257818