Training in progress, epoch 1

config.json

@@ -10,10 +10,10 @@
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
-  "n_embd": 96,
-  "n_head": 8,
+  "n_embd": 600,
+  "n_head": 10,
   "n_inner": null,
-  "n_layer": 4,
+  "n_layer": 10,
   "n_positions": 1024,
   "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:f19a53748ef7829c453fd4887a282f741186e3ba52abc703e6a2e2e651fd108a
-size 21487080
+oid sha256:32cf349f2376579e349e3ce27baa6096f99c7f0c70924050bd3d8077cedbbd92
+size 296203656

tokenizer.json

@@ -1,11 +1,6 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 512,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
+  "truncation": null,
   "padding": null,
   "added_tokens": [
     {