Training in progress, step 500

config.json

@@ -10,7 +10,7 @@
   "initializer_range": 0.02,
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
-  "n_ctx": 1024,
+  "n_ctx": 512,
   "n_embd": 768,
   "n_head": 12,
   "n_inner": null,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cab0d8ba1a2784a79b28ea149a9388bdbfe7e0cedc7694e2bfd86fe38680d2d
+oid sha256:41c24464af4489047c01723074eb42ad3819a667916e434d0f4664e946aba3a4
 size 503128704

runs/Jul12_06-24-44_e1d05e09f637/events.out.tfevents.1720765489.e1d05e09f637.742.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:323178c590a6bc02f4b0593db8dcb4c629526c9743c929b24b78dd812e3e117f
+size 15390

tokenizer.json

@@ -2,7 +2,7 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 1024,
+    "max_length": 512,
     "strategy": "LongestFirst",
     "stride": 0
   },

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21a650ce53321e43bfc0ba16e7717c1b39bdc49e7272e0e7fb9c5d5d404b675e
+oid sha256:7167e37320ade4b4f5f07173b53706f9b362d771735add964c675dafc6ac7a09
 size 5176