Training in progress, step 500

config.json

@@ -1,15 +1,21 @@
 {
-  "_name_or_path": "imthanhlv/gpt2news",
+  "_name_or_path": "danghuy1999/gpt2-viwiki",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
   ],
-  "attn_pdrop": 0.0,
+  "attn_pdrop": 0.1,
   "bos_token_id": 50256,
-  "embd_pdrop": 0.0,
+  "embd_pdrop": 0.1,
   "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,
@@ -19,7 +25,7 @@
   "n_layer": 12,
   "n_positions": 1024,
   "reorder_and_upcast_attn": false,
-  "resid_pdrop": 0.0,
+  "resid_pdrop": 0.1,
   "scale_attn_by_inverse_layer_idx": false,
   "scale_attn_weights": true,
   "summary_activation": null,
@@ -30,11 +36,11 @@
   "task_specific_params": {
     "text-generation": {
       "do_sample": true,
-      "max_length": 150
+      "max_length": 50
     }
   },
   "torch_dtype": "float32",
   "transformers_version": "4.16.2",
   "use_cache": true,
-  "vocab_size": 50259
+  "vocab_size": 50258
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6aa87ac9a8d0352bd848f68c0b448759363578a50f7a7f6d2d637d0537fea59c
-size 510409961
+oid sha256:956d163f87ad360925868ccb723b9ed50d021f73387841469594f881cf54c12b
+size 510406889

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:347eb7d59ce5683875397a53d9f1d0c071861a796b811deec21d5c8426bfb277
+oid sha256:f28080c501c962dc2785f9d48dc852a05b41e6c7083e7462f202dc0719135023
 size 3055