Training in progress, step 5000

config.json

@@ -12,8 +12,8 @@
   "layer_norm_epsilon": 1e-05,
   "model_type": "gpt2",
   "n_ctx": 256,
-  "n_embd": 512,
-  "n_head": 8,
+  "n_embd": 768,
+  "n_head": 12,
   "n_inner": null,
   "n_layer": 12,
   "n_positions": 1024,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7eabd129b09b54afb7dfe57c27a009fcbbe436fa253245beb2efac9ccde9d7b4
-size 214870552
+oid sha256:701303a19dec395d889912204489cfacd1b1d040c4cfb575dfd3979818636c27
+size 435544704

runs/Mar21_02-52-12_gpu-pod/events.out.tfevents.1710989534.gpu-pod.7857.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f82c8e939699eac4120379aee4cc5a6ea116510c16098ce53649d0a067496af3
+size 4857

runs/Mar21_02-55-06_gpu-pod/events.out.tfevents.1710989708.gpu-pod.8674.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d9e7071f2fd972b84ecb03e7c8fc0c6d1cc6753365b0a02544d0cec3bcbf706
+size 4857

runs/Mar21_02-55-53_gpu-pod/events.out.tfevents.1710989755.gpu-pod.8872.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5fc10768ce2769d517d44ee8ec0c05a3a2a432429bd8a5545b70553131216bd
+size 5339

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:059fe3f2639433e1ec2284293fe1424c5a706caf461458b33154f65dc3ff4c59
+oid sha256:58fce5f75166f6d4568cdaa0d32fd2c46e5246a4fa330459de61cb3ab8843108
 size 4475