Training in progress, step 150

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 sha256:327835ed64482e0813eec3da3ed7c89945a19469e6130d86c422222fd26c3bb3
-size 38466
+oid sha256:7c1477cba3e7029e92807ccd27a274e94142fffbf241f21a879b1c5ddb9c2c3d
+size 6400794

tokenizer.json

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

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c261ae201afa7346c0a8b676387b2d338e5ea4a1f10909197dadbaff112013f
+oid sha256:730aa3f0d0dd6487dc020adb3fe55aa66774ebde81e9141e33d66ddeff9b63db
 size 4472