Training in progress, step 10

config.json

@@ -1,6 +1,5 @@
 {
-  "_name_or_path": "ArmanAsq/gpt2_dsm_fa_clm-model-3",
-  "_num_labels": 1,
+  "_name_or_path": "openai-community/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,
@@ -42,5 +35,5 @@
   "torch_dtype": "bfloat16",
   "transformers_version": "4.41.2",
   "use_cache": true,
-  "vocab_size": 54838
+  "vocab_size": 54836
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05e1c85a01ba8b02743216e31ce5e00e0c781d5b493ca79a9bb019aa846ae3a0
-size 170869208
+oid sha256:2861398c119cdddfe42dabfeeab46fe06fba5d0a211a72111420bc6f7389a8d8
+size 255928000