Training in progress, step 2

config.json

@@ -1,11 +1,11 @@
 {
+  "_name_or_path": "gpt2",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
   ],
   "attn_pdrop": 0.1,
   "bos_token_id": 0,
-  "dtype": "float32",
   "embd_pdrop": 0.1,
   "eos_token_id": 0,
   "initializer_range": 0.02,
@@ -17,7 +17,6 @@
   "n_inner": null,
   "n_layer": 12,
   "n_positions": 1024,
-  "pad_token_id": 0,
   "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,
   "scale_attn_by_inverse_layer_idx": false,
@@ -33,7 +32,8 @@
       "max_length": 50
     }
   },
-  "transformers_version": "4.56.2",
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.1",
   "use_cache": true,
   "vocab_size": 50000
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bb72f64f288857fd9520f7d7a37b30447a8e39642292135e2dc73253d63205d
+oid sha256:8120777888c74af794934853065e6a46218fdd7715dc67cbbada18b98344ff3b
 size 496984704

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65cfde8ac21b70ae0532ff6892d7904c10034a580a3e7adaf2fc67e2ad646b52
-size 5777
+oid sha256:3b9ed5fb36b7166d42fe9edcd194bdb43f2cb7c62c7804693007b82710506b2e
+size 5304