Training in progress, epoch 1

config.json

@@ -1,4 +1,5 @@
 {
+  "_name_or_path": "gpt2",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
@@ -10,10 +11,11 @@
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
-  "n_embd": 600,
-  "n_head": 10,
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
   "n_inner": null,
-  "n_layer": 10,
+  "n_layer": 12,
   "n_positions": 1024,
   "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,
@@ -24,8 +26,14 @@
   "summary_proj_to_labels": true,
   "summary_type": "cls_index",
   "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
   "torch_dtype": "float32",
-  "transformers_version": "4.40.1",
+  "transformers_version": "4.40.2",
   "use_cache": true,
   "vocab_size": 50257
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32cf349f2376579e349e3ce27baa6096f99c7f0c70924050bd3d8077cedbbd92
-size 296203656
+oid sha256:143dc67b753bfce0d3e9f0edc155500dc58d5f62ff301953fc33de0e7da9d723
+size 497774208

tokenizer.json

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