Training in progress, step 10000

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "gpt2-medium",
+  "_name_or_path": "/content/MyanmarGPT - previous",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
@@ -12,13 +12,11 @@
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
   "n_ctx": 1024,
-  "n_embd": 1024,
-  "n_head": 16,
+  "n_embd": 768,
+  "n_head": 12,
   "n_inner": null,
-  "n_layer": 24,
+  "n_layer": 12,
   "n_positions": 1024,
-  "n_special": 0,
-  "predict_special_tokens": true,
   "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,
   "scale_attn_by_inverse_layer_idx": false,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47b019be2a89f1b83d91ac9ba19d3824bc8addbbf20c72ed2b0aa76aade63abe
-size 1419322880
+oid sha256:4569809d19f454d109e221beed5db02bbfe9744c43bdeac597eb309882aec7c2
+size 497774208

runs/Dec13_19-19-51_6862dcd86e9a/events.out.tfevents.1702495192.6862dcd86e9a.191.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73091212c44137b5a6326ffc9b828a8aeb87cb2ca35430d5390f3f9a252cd854
+size 7615

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de6356f01f5d2dc37383b24cfbf060d65a8349d336bc137fec32ebca1473d475
+oid sha256:887cde771b6d493f66e03443461a14fbff58c5fba53667686e2c83fc1a1b66c8
 size 4536