Training in progress, step 1560

config.json

@@ -19,10 +19,10 @@
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
   "n_ctx": 1024,
-  "n_embd": 16,
-  "n_head": 2,
+  "n_embd": 128,
+  "n_head": 8,
   "n_inner": null,
-  "n_layer": 2,
+  "n_layer": 8,
   "n_positions": 30,
   "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:490c3fdbbd530ee348977a487f48c694d329dbab6a618566a97d65447223593f
-size 38146
+oid sha256:a1a99ee956ced27cabbbf246e778f46148647460f70704e38249498916396652
+size 6400794

tokenizer.json

@@ -94,16 +94,16 @@
       "<pad>": 1,
       "<mask>": 2,
       "<bos>": 3,
-      "Today": 4,
-      "was": 5,
-      "Bible": 6,
-      "and": 7,
-      ",": 8,
-      ".": 9,
-      "class": 10,
-      "that": 11,
-      "Tuesday": 12,
-      "meant": 13
+      "Tuesday": 4,
+      "that": 5,
+      "and": 6,
+      "Today": 7,
+      "meant": 8,
+      ",": 9,
+      ".": 10,
+      "was": 11,
+      "class": 12,
+      "Bible": 13
     },
     "unk_token": "<unk>"
   }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bb385852763e8c72097d3758fc90729a01ae406ed0bf203f6c31a40d9cda936
-size 4408
+oid sha256:d86cf3b1d355bd091e9e110f95a0fada81eda87e79cf3c112a09ce19a56297d5
+size 4472