Training in progress, epoch 1

config.json

@@ -1,4 +1,5 @@
 {
+  "_name_or_path": "gpt2",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
@@ -10,6 +11,7 @@
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
+  "n_ctx": 1024,
   "n_embd": 768,
   "n_head": 12,
   "n_inner": null,
@@ -24,6 +26,12 @@
   "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",
   "use_cache": true,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63136ebd82a1b8949e51c148c524b1f97899f4786f9e771a18fb3eae09ab9684
+oid sha256:0750a4936fe65637a7c009b1a38d55a640fda129d6de56aebf4f9ac5bf9cf5cf
 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": [
     {