Training in progress, step 500

config.json

@@ -12,7 +12,7 @@
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
   "n_ctx": 40,
-  "n_embd": 768,
+  "n_embd": 120,
   "n_head": 12,
   "n_inner": null,
   "n_layer": 12,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ad2997a91f2f2e94507dc9f612c62d8fff72eca123e76a3339a9e7896da5207
-size 497774208
+oid sha256:202d3124a99d8f1d279d334c1d067289c528950e52cf5b147f5c532af7d6b504
+size 32999512

runs/Jun20_19-07-12_255c5f7d24c6/events.out.tfevents.1718910435.255c5f7d24c6.1923.11

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6918ed663f0c3fa4483c07aad362d4d23ae3bd7d5ec9d395d1fe01696753e724
+size 10699

runs/Jun20_19-07-45_255c5f7d24c6/events.out.tfevents.1718910468.255c5f7d24c6.1923.12

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d14061e0876712c2ee8b227a33520fedc1dbd2f72ecf6dd38430491abd2a04eb
+size 10779

runs/Jun20_19-11-50_255c5f7d24c6/events.out.tfevents.1718910714.255c5f7d24c6.1923.13

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53769296341b2ebbb33e6d8abc3dd42f4aa86f6d054bc332b291f222123ab9dc
+size 5732

runs/Jun20_19-14-40_255c5f7d24c6/events.out.tfevents.1718910883.255c5f7d24c6.1923.14

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec5a2828d62f45b5e1de2d216ddd8939a940e1a73f6570f36b112c746801b8bd
+size 18042

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9363a5cd8ce3b6e87dbfeac12a0d5cefad8a218b2fb1d1e226cf3024c378ece
+oid sha256:6d6c06ebd8ae223016f32353fdff7361ee5e395a4740586f04a69d8ac6ad8af3
 size 5176