Training in progress, epoch 1

config.json

@@ -11,10 +11,10 @@
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
   "n_ctx": 128,
-  "n_embd": 128,
-  "n_head": 2,
+  "n_embd": 256,
+  "n_head": 4,
   "n_inner": null,
-  "n_layer": 4,
+  "n_layer": 6,
   "n_positions": 128,
   "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b477b1e9558bb1b9d0bdb428a9b73fcb37a9b43cfdca1ca41a1bcb5f5e0973e1
-size 18603952
+oid sha256:959a4a87c2a722b53d8c38dae4b17e88c2a0d8b99e08b0f1b06eb4b52d5fa573
+size 49814856

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f1e18ca3d4654e92f33e686946fef31bd6d3bf3d5fe3e7b15b7b80131a52f19
+size 5304