Training in progress, step 500

config.json

@@ -1,6 +1,5 @@
 {
-  "_name_or_path": "distilgpt2",
-  "_num_labels": 1,
+  "_name_or_path": "gpt2",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
@@ -9,20 +8,14 @@
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
   "eos_token_id": 50256,
-  "id2label": {
-    "0": "LABEL_0"
-  },
   "initializer_range": 0.02,
-  "label2id": {
-    "LABEL_0": 0
-  },
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
   "n_ctx": 1024,
   "n_embd": 768,
   "n_head": 12,
   "n_inner": null,
-  "n_layer": 6,
+  "n_layer": 12,
   "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 sha256:5a988075e8b7fe5b99273707075bf984354e5ceecf8303486a264319bac13542
-size 327657928
+oid sha256:5609ac6f01101d2bcb425aa64610463292a0fe69c5001c2522d8c213dfd822b8
+size 497774208

runs/Dec26_14-07-41_4f87fa13cf4f/events.out.tfevents.1735222063.4f87fa13cf4f.45582.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42d90d36507cff8dc7b5c73957e780c540998ad2791ba8de0f4eaa382f5d1d9d
+size 5919

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd4f2906cbf2f7f7bbd40826ec841400a6fa3bcde012ac5923d5be7e0c0c23fa
+oid sha256:9f301c938db1cb6977900c5e27614e30ccd7fd4df22c121c98fedc0e91b2cf20
 size 5240