Training in progress, step 203

config.json

@@ -8,15 +8,15 @@
   "eos_token_id": 31989,
   "head_dim": 64,
   "hidden_act": "silu",
-  "hidden_size": 576,
-  "initializer_range": 0.02,
-  "intermediate_size": 1536,
+  "hidden_size": 768,
+  "initializer_range": 0.036084391824351615,
+  "intermediate_size": 1920,
   "max_position_embeddings": 8192,
   "mlp_bias": false,
   "model_type": "llama",
-  "num_attention_heads": 9,
-  "num_hidden_layers": 30,
-  "num_key_value_heads": 3,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 4,
   "pad_token_id": 31989,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-06,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb83ffd9c111716ef3945fedef6c5cfbbf22917e3a5f376b5318fbc344731ef8
-size 249301400
+oid sha256:ba2d283766394519148bce4ab8a435eab2a40cccd78e648578f50e8075709f5c
+size 337085840