Training in progress, epoch 1

config.json

@@ -1,5 +1,4 @@
 {
-  "_name_or_path": "gpt2",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
@@ -11,11 +10,10 @@
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
-  "n_ctx": 1024,
-  "n_embd": 768,
-  "n_head": 12,
+  "n_embd": 96,
+  "n_head": 8,
   "n_inner": null,
-  "n_layer": 12,
+  "n_layer": 4,
   "n_positions": 1024,
   "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,
@@ -26,12 +24,6 @@
   "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:b87d089352db00697642036a3fdfa154ff2227f1966d2d379dd4ca9a4fb4523e
-size 497774208
+oid sha256:f19a53748ef7829c453fd4887a282f741186e3ba52abc703e6a2e2e651fd108a
+size 21487080

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": [
     {