Training in progress, step 500

config.json

@@ -1,21 +1,14 @@
 {
-  "_name_or_path": "danghuy1999/gpt2-viwiki",
+  "_name_or_path": "NlpHUST/gpt2-vietnamese",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
   ],
-  "attn_pdrop": 0.1,
+  "attn_pdrop": 0.0,
   "bos_token_id": 50256,
-  "embd_pdrop": 0.1,
+  "embd_pdrop": 0.0,
   "eos_token_id": 50256,
-  "gradient_checkpointing": false,
-  "id2label": {
-    "0": "LABEL_0"
-  },
   "initializer_range": 0.02,
-  "label2id": {
-    "LABEL_0": 0
-  },
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
   "n_ctx": 1024,
@@ -25,7 +18,7 @@
   "n_layer": 12,
   "n_positions": 1024,
   "reorder_and_upcast_attn": false,
-  "resid_pdrop": 0.1,
+  "resid_pdrop": 0.0,
   "scale_attn_by_inverse_layer_idx": false,
   "scale_attn_weights": true,
   "summary_activation": null,
@@ -42,5 +35,5 @@
   "torch_dtype": "float32",
   "transformers_version": "4.47.1",
   "use_cache": true,
-  "vocab_size": 50257
+  "vocab_size": 50258
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b168887df5cf10b2f0868d073824c4cb38c740dc137f1e0a90691b01089e039
-size 497774208
+oid sha256:87ed5f2b3a8d0d14300a3d7806be3dd0023c62f1a98ddbe3d24c08f7580e87c6
+size 497777280

runs/Dec30_13-43-46_b2ab2675858f/events.out.tfevents.1735566227.b2ab2675858f.51401.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbf65636e4b66c5305322e906ca4bcecd113e384d828f707e0d32d09bb2017e9
+size 6352

special_tokens_map.json

@@ -2,14 +2,14 @@
   "bos_token": {
     "content": "<|endoftext|>",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },
   "eos_token": {
     "content": "<|endoftext|>",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   },
@@ -17,7 +17,7 @@
   "unk_token": {
     "content": "<|endoftext|>",
     "lstrip": false,
-    "normalized": true,
+    "normalized": false,
     "rstrip": false,
     "single_word": false
   }

tokenizer_config.json

@@ -3,9 +3,49 @@
   "add_prefix_space": false,
   "added_tokens_decoder": {
     "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50257": {
       "content": "<|endoftext|>",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:026df79ea96a07de596515546a8d94d151f4612a00707659bcb75920afaf3ed1
+oid sha256:aad7938374aec1af6e11b2aa4425db64eb565408386b4652f78474adfb0ea9cb
 size 5368